# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(department(s)? of |in\n)(\w+ ?\w+[^,]?\w+[^,]?\w+[ ]?\w+[ ]?\w+)"
test_str = ("Virginia Tech Sample:\n"
"A COMPARISON OF THE EFFICIENCY AND EFFECTIVENESS\n"
"OF TWO MODELS FOR DETERMINING THE COST\n"
"OF SPECIAL EDUCATION PROGRAMS\n"
"by\n"
"Kenneth L. Kienas\n"
"Dissertation submitted to the Faculty of the\n"
"Virginia Polytechnic Institute and State University\n"
"in partial fulfillment of the requirements for the degree of\n"
"DOCTOR OF EDUCATION\n"
"in\n"
"Administration and Supervision of Special Education\n"
"APPRQVED:\n"
"Richard G. Salmon, Co-Chairman Phili R. Jones, Co-Chairman\n"
"John A. McLaughlin Shirley A Jones\n"
"Shirley A. Underwood\n"
"May, 1986\n"
"Blacksburg, Virginia\n"
"--------------------------------------------------------\n"
"MIT Sample:\n"
"THE RESPONSE OF CONTINUOUS SYSTEMS\n"
"TO RANDOM NOISE FIELDS\n"
"by \n"
"Richard H. Lyon\n"
"A. B., Evansville College, 1952\n"
"Submitted in Partial Fulfillment of the\n"
"Requirements for the Degree of\n"
"Doctor of Philosophy\n"
"at the\n"
"MASSACHUSETTS INSTITUTE OF TECHNOLOGY\n"
"June, 1955\n"
"Signature of Author\n"
"department of Physics, May 16, 1955\n"
"Certified by\n"
"Thesis Supervisor\n"
"Accepted by\n"
"Chairman, Departmental Committee on Graduate, Students\n"
"---------------------------------------------------------\n"
"MIT Sample:\n"
"ON THE MECHANICS OF TWIST INSERTION\n"
"by\n"
"ALY H, M, EL-SHIEKH\n"
"B.Sc. University of Alexandria, U.A.R.\n"
"1956\n"
"S.M. Massachusetts Institute of Technology\n"
"1961\n"
"M.E. Massachusetts Institute of Technology\n"
"1964\n"
"Submitted in Partial Fulfillment\n"
"of the Requirements for the\n"
"Degree of Doctor of Science\n"
"at the\n"
"MASSACHUSETTS INSTITUTE OF TECHNOLOGY\n"
"May 1965\n"
"Signature of the Author\n"
"department of Mechanical Engineering\n"
"Fibers and Polymers Division\n"
"Certified by\n"
"Thesis Supervisor\n"
"Accepted by\n"
"Chairman Departmental Committee on Graduate Students\n"
"------------------------------------------------------------\n"
"MIT Sample:\n"
"HYDRAULIC DAMPER DESIGN\n"
"FOR A KNEE PROSTHESIS\n"
"by\n"
"Eric Hershler Bott\n"
"Submitted in Partial Fulfillment\n"
"of the Requirements for the\n"
"Degree of Bachelor of Science\n"
"at the\n"
"MASSACHUSETTS INSTITUTE OF TECHNOLOGY\n"
"February, 1975\n"
"Signature of Author\n"
"departments of Mechanical Engineering and\n"
"Physics, February 23, 1975\n"
"Certified by\n"
"Thesis Supervisor\n"
"Accepted by\n"
"Chairman, Departmental Committee on Theses\n"
"MAR 15 1976\n"
"LIBRARIES\n"
"------------------------------------------------------------\n"
"Virginia Tech Sample:\n"
"ASSESSMENT OF A MENTOR PROGRAM\n"
"ON SELF-CONCEPT AND ACHIEVEMENT VARIABLES\n"
"OF MIDDLE SCHOOL UNDERACHIEVERS\n"
"by\n"
"Helene Aiello\n"
"Dissertation submitted to the faculty of the Virginia\n"
"Polytechnic Institute and State University in partial\n"
"fulfillment of the requirements for the degree of\n"
"Doctor of Education\n"
"in\n"
"Administration and Supervision\n"
"Of\n"
"Special Education\n"
"APPROVED:\n"
"Philip R. Jones, Chairman Kenneth Underwood\n"
"Sylvia Auton\n"
"Shirley Jones Ronald McKeen\n"
"February 22, 1988\n"
"Blacksburg, Virginia")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html